© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115802
    Prev
    Next
    INDEX
    Explanations

    vandalism graffiti removal

    np_acts-logits-general · gemini-2.5-flash-lite

    focusing on deep analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    詞
    0.52
    INATION
    0.48
     (
    0.47
    事
    0.44
    間
    0.43
    ｾ
    0.43
    日
    0.43
    變
    0.42
    人
    0.42
     SUPPL
    0.42
    POSITIVE LOGITS
    trashItem
    0.57
    gène
    0.54
     さらに
    0.54
     ácido
    0.54
     appliquée
    0.54
     Séb
    0.52
     elaborado
    0.52
     équipe
    0.51
     крупней
    0.51
     desafío
    0.51
    Activations Density 0.001%

    No Known Activations